Current approaches for mining big data such as streaming have fundamental limitations on the kind of mining that can be performed. However, machines with hundreds of GB of RAM are available nowadays. This workshop will focus on novel data mining algorithms that use RAM effectively by mining data stored in compact or compressed formats. A key underlying theme will be the application of compressed and succinct data structures including FM-index, wavelet trees, compressed suffix arrays, XBW etc. and their application to data mining.

The workshop, to be held in conjunction with ICDM 2013, invites submissions on aspects of data mining that focus on in-core mining of large data sets including but not limited to:

- applications involving large-scale in-memory data or text mining
- data mining algorithms on compressed data
- novel memory-efficient data structures and algorithms for large-scale data mining
- indexing algorithms for machine learning and classification
- memory hierarchy optimizations in data mining algorithms
- succinct or compressed data structures motivated by problems in data mining

Papers emphasizing theoretical foundations, algorithms, novel use of data compression, and applications are particularly welcome. Submitted papers will be assessed based on the novelty of approach, scientific rigour, relevance to the themes of the workshop and clarity of writing. For papers that rely heavily on empirical evaluations, the experimental methods and results should be clear, well executed, and repeatable. Submitting authors are strongly encouraged to make data and code available whenever possible.